Feras A. Profile

LÖYDÄ

Data Processing

Data Science

Excel

Machine Learning (ML)

Python

5,0

(2 arvostelua)

Seuraat nyt käyttäjää .

Virhe seurattaessa käyttäjää.

Tämä käyttäjä ei salli käyttäjien seurata häntä.

Seuraat jo tätä käyttäjää.

Jäsenyystasosi mahdollistaa vain 0 seurausta. Päivitä tästä.

Poistit käyttäjän seurannan onnistuneesti.

Virhe poistettaessa käyttäjän seurantaa.

Olet onnistuneesti suositellut käyttäjää

Virhe suositeltaessa käyttäjää.

Jokin meni vikaan. Päivitä sivu ja yritä uudelleen.

Sähköposti vahvistettu onnistuneesti.

$12 USD / tunti

dammam,

saudi arabia

$12 USD / tunti

Kello on tällä hetkellä 3:09 ip. täällä

Liittynyt maaliskuuta 11, 2021

0 Suosittelee

Feras A.

@ferasalshaheen

5,0

(2 arvostelua)

1,4

$12 USD / tunti

dammam,

saudi arabia

$12 USD / tunti

100 %

Suoritetut työt

100 %

Budjetin mukaisesti

100 %

Aikataulussa

Ei saatavilla

Uudelleenpalkkausaste

Expert Data Analyst | Python | Excel | Alteryx

Feras is an expert data analyst and certified from Computing Technology Industry Association (CompTIA) by earning CompTIA Data Plus Certification. Feras has a strong background in: - Descriptive and Inferential Statistics - Financial, Operational, and Marketing Analysis - Business Planning - Mentorship in the field of data analysis - Writing Analytical Reports - Building Visual Dashboards using Tableau and Microsoft Excel - Machine Learning Modeling using Scikit Learn - Deep learning Modeling using Pytorch Feras is also proficient in conducting data analysis using - Python - Microsoft Excel - Alteryx. . Feras has worked on multiple projects in the data analysis field. Some of the main projects are: - conducting an A/B test analysis for an e-commerce company - Exploring and studying the most popular venues in three major cities in Saudi Arabia - Building recommendation system for IBM articles to recommend articles for readers. Feras will deliver high quality jobs within a timely manner, provide quick response, and offer thorough guidance during consultation sessions. Feel free to contact me anytime. Thanks for your consideration !

Katso kaikki Python Developers paikassa Saudi Arabia

Ota yhteyttä käyttäjään Feras A. työhösi liittyen

Kirjaudu sisään keskustellaksesi yksityiskohdista chatin välityksellä.

Portfoliokohteet

The aim of the project is to detect faults in electrical transmission system and classify the fault based on current and voltage measurement.

After analyzing the fault types shown in the file it was found that the majority of the faults are 3 phase faults, where they make 40% of the faults. The other types of the faults, each make 20% of the faults occurring on the transmission line. Finally, it was found that 20% of the faults occurring on phase A only, while 40% faults includes phase A. Suggesting an issue related to phase A of the transmission line

I used the following libraries in my project:
1- Pandas to read CSV file, wrangle the data, and perform exploratory analysis
2- matplotlib and seaborn for data visualization and as part of data exploratory analysis.
3- Sklearn to build the classification model and to measure the model accuracy.

Electrical Fault Detection

Project motivation: Photo sharing and photo storage services like to have location data for each photo that is uploaded. With the location data, these services can build advanced features, such as automatic suggestion of relevant tags or automatic photo organization, which help provide a compelling user experience. Although a photo's location can often be obtained by looking at the photo's metadata, many photos uploaded to these services will not have location metadata available. This can happen when, for example, the camera capturing the picture does not have GPS or if a photo's metadata is scrubbed due to privacy concerns.

If no location metadata for an image is available, one way to infer the location is to detect and classify a discernable landmark in the image. Given the large number of landmarks across the world and the immense volume of images that are uploaded to photo sharing services, using human judgement to classify these landmarks would not be feasible.

Classifying Landmark using Convolutional Neural Network CNN

The aim of the project is to extract data from different sources, clean them, and prepare them for analysis and extracting insights. The data set I chose to analyze is from WeRateDogs. WeRateDogs is a Twitter account that rates people's dogs with a humorous ratings and comment about the dog. The data was extracted using tweeter API combined with CSV file provided by Udacity. The outcomes of the analysis are the following:

1- It can be seen from the generated word cloud that the most common breeds of dogs are: Chihuahua, Labrador retriever, and the golden retriever.
2- Labrador has the highest retweets and likes, the golden retriever comes second, and the Chihuahua comes last in both retweets and likes.
3- The average rating for golden retriever is the highest which is 11.5, Labrador comes second with average rating of 11.3, and the Chihuahua comes last with rating of 10.7

Analyzing Tweets from WeRateDogs Twitter account

The aim of the project is to study and visualize the revenue of the integrated oil and gas sector from 2012 to 2018 and build a dashboard through Microsoft Excel. The major findings of my analysis are:

1- The Integrated Oil & Gas sub-sector makes around 16% out of the energy sector in New York Stock Exchange Market. Making it a potential sector for investment.

2- the total revenue of the Integrated Oil & Gas subsector starting from 2012 along with the forecasted revenue from 2016 to 2018. This forecast is built over the worst case scenario, yet it expects a growth in revenue even higher than before. This support the first point stating the amount of potential expected from this sub-sector .

Dashboard is attached along with the Excel Sheet used to build it

Analyzing Integrated Oil & Gas Sector in NYSE Market

The aim of the project was to analyze the cancelation trend for US Airlines during 2015 and find insights about the that trend. The trending was visualized through a dashboard using Tableau. In summary the following main major points found:

1- The state with highest number of cancelled flights is Texas, which represents 15% out of the total number of cancelled flights. Also, it was found that February being the month with highest number of cancellation and having more than 1000 flights cancelled. As per the resource mentioned in the attached report, this was due bad weather condition. Moreover, the reference also states that Dallas Fort Worth Airport had one of the highest number of flights cancelled due to the aforementioned reason.

2- Weather is the main cause for flight cancellation for more than 50% precent of the flights in the US in 2015. Second in order comes airline or carrier related problems causing about 30% of flights cancellation.

Analyzing Flight Cancelation for US Airlines in 2015

The purpose of this project is to create recommendation system for readers on IBM Watson. Three different techniques were used to built the system:
1- Ranking based recommendation system
2- Content based recommendation system to provide recommendation based on similarity between articles
3- Collaborative filtering based recommendation system to provide recommendation based on similarity between readers

The Jupytor notebook is attached showing the full work

IBM article recommendation system

Arvostelut

Muutokset tallennettu

Näytetään 1 - 2 / 2 arvostelua

Suodata arvosteluja:

5,0

₹3 200,00 INR

Web scrapping of data

Mr. Feras delivered satisfactory work as he promised. Sure I will hire him again for my future work.

Abhishet Kumar G.

@abhisprout20

•

5 kuukautta sitten

5,0

$20,00 AUD

Python Data Analysis

Exceptional skills, easy to work with didn't need any guidence just went of brief description I gave him. Looking forward to working with him again.

Python

Machine Learning (ML)

Data Science

Sabyasachi D.

@debsabyasachi

•

6 kuukautta sitten

Kokemus

Udacity

lokak. 2021 - Voimassa

As a consultant to educational platform, such as Udacity, I utilize my specialized knowledge in the field of data analysis and my strong communication skills to provide mentorship and other student support services.

Confidential

lokak. 2016 - Voimassa

• Developing business plans. • Budgeting and cost analysis. • Analyzing asset performance • Planning and project management • Trending and analyzing plant interruptions related to electrical systems • Performing risk assessments

Koulutus

Electrical Engineering

King Fahd University of Petroleum & Minerals,

Saudi Arabia

2011 - 2016

(5 vuotta)

Pätevyydet

CompTIA

2022

CompTIA Data+ is an early-career data analytics certification for professionals tasked with developing and promoting data-driven business decision-making.

IBM

2021

In this Professional Certificate, I developed and honed hands on skills in Data Science and Machine Learning. Starting with an orientation of Data Science and its Methodology, became familiar and used a variety of data science tools, learned Python and SQL, performed Data Visualization and Analysis, and created Machine Learning models. In the process I completed several labs and assignments on the cloud including a Capstone Project at the end to apply and demonstrate their knowledge and skills

Udacity

2021

This Nanodegree program aims to advance my programming skills and refine my ability to work with messy, complex datasets. Through it I learned to manipulate and prepare data for analysis, and create visualizations for data exploration. Finally, I learned to utilize my data skills to tell a story with data.

Julkaisut

Building Your First Neural Network Using Keras

Meduim

In this article I give a tutorial that will help readers to build their start-up model. First, I start by explaining the basic concepts of neural network model. Then presenting the model architecture in Python. After that I list the hyperparameters used for tuning the model and change its complexity. Finally, I share links to some courses that would help starting to learn more about this field and to go further in it.

Starbucks’ Customer Response Analysis Project

Meduim

In this article I explain methodology of performing data analysis by going through on the projects I worked on as Udacity student. In this project I analyze customers response by looking and working with data extracted from an app that mimics Starbucks actual mobile app where a certain type of offer is sent to certain customers and it tracks their response. This simulation, unlike the actual app, has only one product and it sends the offer every few days for 30 days.